The key to discover potential opportunity information in business process is to identify the primary roles and actors, i.e., how to obtain their associations according to interactive behaviors in business processes with the social network. The identification of primary roles is generally studied by the influence of actors and statuses in social network, but ignores that self-roles influence on social network. This paper focuses on the above problem and discusses the relationship of roles and actors from two different networks. By quantifying the similarity of actors, the information entropy of roles is defined to improve the accuracy of identification. Then we propose an approach to obtain the potential opportunity information combining with the significance of roles and actors. Specifically, the identification of roles and actors is based on the further comparison with their significance. The result of experimental simulation case study shows that the potential opportunity information does not only depend on the position of actors in the social network but also on resource or the self-roles.
{"title":"Role Identification to Discover Potential Opportunity Information in Business Process","authors":"Lu Zhao, Wenan Tan, Xiande Fang","doi":"10.1109/ICEBE.2017.20","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.20","url":null,"abstract":"The key to discover potential opportunity information in business process is to identify the primary roles and actors, i.e., how to obtain their associations according to interactive behaviors in business processes with the social network. The identification of primary roles is generally studied by the influence of actors and statuses in social network, but ignores that self-roles influence on social network. This paper focuses on the above problem and discusses the relationship of roles and actors from two different networks. By quantifying the similarity of actors, the information entropy of roles is defined to improve the accuracy of identification. Then we propose an approach to obtain the potential opportunity information combining with the significance of roles and actors. Specifically, the identification of roles and actors is based on the further comparison with their significance. The result of experimental simulation case study shows that the potential opportunity information does not only depend on the position of actors in the social network but also on resource or the self-roles.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"96 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127992777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Used mainly for the virtual money, the Blockchain technology adopts a decentralized network of peers to ensure a secure and transparent information storage and transmission. The basic use of Blockchain can be bypassed, and it is interesting to integrate it into other fields such as the Cloud storage. Cloud storage solutions ensure a continuous data synchronization and guarantee data sharing between different users. However, sharing user side encrypted data raises key and access control management challenges. Within this paper, we propose a novel access control model called Timely CP-ABE. Two main features come with our model. First, we introduce a decentralized access control mechanism where the user legitimacy is verified by Blockchain nodes. Second, we add temporal dimension to file sharing based on CP-ABE. In fact, we introduce a validity time to the access authorization without additional revocation cost. As a proof of concept, the implementation of the Timely CP-ABE based on Blockchain is performed on the CP-ABE toolkit and Multichain solution.
{"title":"Decentralized Access Control Mechanism with Temporal Dimension Based on Blockchain","authors":"Mayssa Jemel, A. Serhrouchni","doi":"10.1109/ICEBE.2017.35","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.35","url":null,"abstract":"Used mainly for the virtual money, the Blockchain technology adopts a decentralized network of peers to ensure a secure and transparent information storage and transmission. The basic use of Blockchain can be bypassed, and it is interesting to integrate it into other fields such as the Cloud storage. Cloud storage solutions ensure a continuous data synchronization and guarantee data sharing between different users. However, sharing user side encrypted data raises key and access control management challenges. Within this paper, we propose a novel access control model called Timely CP-ABE. Two main features come with our model. First, we introduce a decentralized access control mechanism where the user legitimacy is verified by Blockchain nodes. Second, we add temporal dimension to file sharing based on CP-ABE. In fact, we introduce a validity time to the access authorization without additional revocation cost. As a proof of concept, the implementation of the Timely CP-ABE based on Blockchain is performed on the CP-ABE toolkit and Multichain solution.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123407284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Business rules could be used to guide the composition of testing cases. However it is difficult for companies to represent or gain their business rules merely depending upon domain experts. Meanwhile, historic testing cases accumulated during previous testing projects provide valuable materials for digging business rules. In this paper, a framework is proposed to extract business rules automatically from historic testing cases to help testing engineers to write new testcases. Firstly, keywords are extracted from historic testing cases based on frequency and freedom of acquired attribute-value pairs. Then, testing cases will be clustered based on semantic similarity of the extracted keywords. Business rules will be discovered and represented by attribute-value pairs. Finally, a case study is demonstrated to verify the validity of the framework.
{"title":"A Framework of Business Rule Extraction from Historic Testing Cases","authors":"Chuyang Jin, Feng Gu, Boyi Xu, Hongming Cai, Chenxi Huang, Yifei Zhang","doi":"10.1109/ICEBE.2017.47","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.47","url":null,"abstract":"Business rules could be used to guide the composition of testing cases. However it is difficult for companies to represent or gain their business rules merely depending upon domain experts. Meanwhile, historic testing cases accumulated during previous testing projects provide valuable materials for digging business rules. In this paper, a framework is proposed to extract business rules automatically from historic testing cases to help testing engineers to write new testcases. Firstly, keywords are extracted from historic testing cases based on frequency and freedom of acquired attribute-value pairs. Then, testing cases will be clustered based on semantic similarity of the extracted keywords. Business rules will be discovered and represented by attribute-value pairs. Finally, a case study is demonstrated to verify the validity of the framework.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123093152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Si Chen, Rui Shi, Zhuangyu Ren, Jiaqi Yan, Yani Shi, Jinyu Zhang
Recent quality scandals reveal the importance of quality management from a supply chain perspective. Although there has been many related studies focusing on supply chain quality management, the technologies used still have difficulties in resolving problems arising from the lack of trust in supply chains. The root reason lies in three challenges brought to the traditional centralized trust mechanism: self-interests of supply chain members, information asymmetry in production processes, costs and limitations of quality inspections. Blockchain is a promising technology to address these problems. In this paper, we discuss how to improve the supply chain quality management by adopting the blockchain technology, and propose a framework for blockchain-based supply chain quality management.
{"title":"A Blockchain-Based Supply Chain Quality Management Framework","authors":"Si Chen, Rui Shi, Zhuangyu Ren, Jiaqi Yan, Yani Shi, Jinyu Zhang","doi":"10.1109/ICEBE.2017.34","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.34","url":null,"abstract":"Recent quality scandals reveal the importance of quality management from a supply chain perspective. Although there has been many related studies focusing on supply chain quality management, the technologies used still have difficulties in resolving problems arising from the lack of trust in supply chains. The root reason lies in three challenges brought to the traditional centralized trust mechanism: self-interests of supply chain members, information asymmetry in production processes, costs and limitations of quality inspections. Blockchain is a promising technology to address these problems. In this paper, we discuss how to improve the supply chain quality management by adopting the blockchain technology, and propose a framework for blockchain-based supply chain quality management.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126835353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Classic collaborative filtering methods suffer from lack of accuracy when it comes to todays complicated ecommerce websites. Recommender systems can be more efficient and effective by considering each user behavior model individually and in groups with other people that can be interpreted as their social relations. This paper presents a new context aware and behavior-based recommender system which utilizes social network analysis to enhance recommending results. The general idea is extracting user behavior patterns in different context based on user's past interactions with the system for further classifications. In this study we use the idea of using social network analysis with an improvement; we consider multiple relations among users and use a multi-layer social network to make our groups of preferences richer. Different social network metrics such as centralization, modularity class and so on can help us find similar groups of users in social network. We combine all the results and suggest top-K items to the user based on his/her nearest neighbor opinions. Evaluating the results shown significant improvement in accuracy of recommendations for proposed approach in contrast to previous techniques.
{"title":"A Context-Aware and User Behavior-Based Recommender System with Regarding Social Network Analysis","authors":"Mina Razghandi, Seyed Alireza Hashemi Golpaygani","doi":"10.1109/ICEBE.2017.40","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.40","url":null,"abstract":"Classic collaborative filtering methods suffer from lack of accuracy when it comes to todays complicated ecommerce websites. Recommender systems can be more efficient and effective by considering each user behavior model individually and in groups with other people that can be interpreted as their social relations. This paper presents a new context aware and behavior-based recommender system which utilizes social network analysis to enhance recommending results. The general idea is extracting user behavior patterns in different context based on user's past interactions with the system for further classifications. In this study we use the idea of using social network analysis with an improvement; we consider multiple relations among users and use a multi-layer social network to make our groups of preferences richer. Different social network metrics such as centralization, modularity class and so on can help us find similar groups of users in social network. We combine all the results and suggest top-K items to the user based on his/her nearest neighbor opinions. Evaluating the results shown significant improvement in accuracy of recommendations for proposed approach in contrast to previous techniques.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127407791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the enforcement of the policies of opening and sharing information resources, protection of citizens' privacy has become a key issue concerned by the government and public. This paper discusses the risk of citizens' privacy disclosure related to government data publishing, and analyzes the main privacy-preserving methods for data publishing. Aiming at the problem that most of the existing privacy protection models for data publishing cannot resist the attacks based on the growing background knowledge, a differential privacy framework for publishing governmental statistical data is established. Based on the framework, a data publishing algorithm using MaxDiff histogram is proposed. Applying differential method, Laplace noises are added to the original dataset, which prevents citizens' privacy from disclosure even if attackers get strong background knowledge. According to the maximum frequency difference, the adjacent data bins are grouped, then the differential privacy histogram with minimum average error can be constructed. Through theoretical analysis and experimental comparison, it is demonstrated that the proposed data publishing algorithm can not only be used to effectively protect citizens' privacy, but also reduce the query sensitivity and improve the utility of the data published.
{"title":"Research on Government Data Publishing Based on Differential Privacy Model","authors":"Chunhui Piao, Yajuan Shi, Yunzuo Zhang, Xuehong Jiang","doi":"10.1109/ICEBE.2017.21","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.21","url":null,"abstract":"With the enforcement of the policies of opening and sharing information resources, protection of citizens' privacy has become a key issue concerned by the government and public. This paper discusses the risk of citizens' privacy disclosure related to government data publishing, and analyzes the main privacy-preserving methods for data publishing. Aiming at the problem that most of the existing privacy protection models for data publishing cannot resist the attacks based on the growing background knowledge, a differential privacy framework for publishing governmental statistical data is established. Based on the framework, a data publishing algorithm using MaxDiff histogram is proposed. Applying differential method, Laplace noises are added to the original dataset, which prevents citizens' privacy from disclosure even if attackers get strong background knowledge. According to the maximum frequency difference, the adjacent data bins are grouped, then the differential privacy histogram with minimum average error can be constructed. Through theoretical analysis and experimental comparison, it is demonstrated that the proposed data publishing algorithm can not only be used to effectively protect citizens' privacy, but also reduce the query sensitivity and improve the utility of the data published.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133705074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chao Guo, Jingchang Guo, Lu Ji, Mingliang Chen, L. Tian
Business intelligence and big data analytics have become increasingly important in both academic and business communities over the past decades. Nuclear power projects involve various bulk materials and the quantities are huge. However, bulk material management in design, procurement and construction phases is disjointed to an extent thus often causes inaccurate purchase quantity of bulk materials, mismatching of upstream and downstream business schedules, poor coordination between different business segments and etc. As a result there are usually large quantities of bulk materials left at the end of the project causing huge waste. Therefore, we developed Bulk Material Management System based on the source data of Design Institute. By calculating quantities of materials as per engineering drawings we can not only provide procurement department with accurate purchase quantities for reference, but also provide construction department with amount of materials in certain installation areas. Then we do research on material balance and add time attribute to the demand materials on field and the received materials after purchasing so as to link the material items with the schedule, cost and other factors. On this basis we develop material balance report of demand quantity, received quantity and inventory quantity in order to make business intelligence analysis for procurement planning, inventory warning, etc. and thus lead to a better EPC coordination for cost and profit efficiency of the company.
{"title":"Development of Bulk Material Management System and Research on Material Balance Applications Based on Business Intelligence","authors":"Chao Guo, Jingchang Guo, Lu Ji, Mingliang Chen, L. Tian","doi":"10.1109/ICEBE.2017.15","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.15","url":null,"abstract":"Business intelligence and big data analytics have become increasingly important in both academic and business communities over the past decades. Nuclear power projects involve various bulk materials and the quantities are huge. However, bulk material management in design, procurement and construction phases is disjointed to an extent thus often causes inaccurate purchase quantity of bulk materials, mismatching of upstream and downstream business schedules, poor coordination between different business segments and etc. As a result there are usually large quantities of bulk materials left at the end of the project causing huge waste. Therefore, we developed Bulk Material Management System based on the source data of Design Institute. By calculating quantities of materials as per engineering drawings we can not only provide procurement department with accurate purchase quantities for reference, but also provide construction department with amount of materials in certain installation areas. Then we do research on material balance and add time attribute to the demand materials on field and the received materials after purchasing so as to link the material items with the schedule, cost and other factors. On this basis we develop material balance report of demand quantity, received quantity and inventory quantity in order to make business intelligence analysis for procurement planning, inventory warning, etc. and thus lead to a better EPC coordination for cost and profit efficiency of the company.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133235717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. HernanE.Villanueva, Alireza Faed, M. MiguelA.Truffa
This article is designed and developed a model of knowledge for a customer relationship management strategy that controls and manages the satisfaction of customers by their claims and feedback conducted and run by the CommonKADS methodology. Emphasis is mainly focused on the vision of the strategy according to the knowledge and the importance of knowledge as an engine for the strategy and specific knowledge domain using schemas. This article identifies the reasoning to manage customers' satisfaction and is translated into rules of inferences. Subsequently, the model is deployed in the tool of visual technology known as Visirule rules. As a result, the driven type of knowledge that can be utilized for the further development of an intelligent system to administer customer satisfaction by their claims.
{"title":"Knowledge Model to Manage Customer Satisfaction Based on Claims","authors":"A. HernanE.Villanueva, Alireza Faed, M. MiguelA.Truffa","doi":"10.1109/ICEBE.2017.38","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.38","url":null,"abstract":"This article is designed and developed a model of knowledge for a customer relationship management strategy that controls and manages the satisfaction of customers by their claims and feedback conducted and run by the CommonKADS methodology. Emphasis is mainly focused on the vision of the strategy according to the knowledge and the importance of knowledge as an engine for the strategy and specific knowledge domain using schemas. This article identifies the reasoning to manage customers' satisfaction and is translated into rules of inferences. Subsequently, the model is deployed in the tool of visual technology known as Visirule rules. As a result, the driven type of knowledge that can be utilized for the further development of an intelligent system to administer customer satisfaction by their claims.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125234259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Alghamdi, Walayat Hussain, Abdulaziz Alharthi, Abdulla Badar Almusheqah
Due to the cost-effectiveness and scalable features of the cloud the demand of its services is increasing every next day. Quality of Service (QOS) is one of the crucial factor in forming a viable Service Level Agreement (SLA) between a consumer and the provider that enable them to establish and maintain a trusted relationship with each other. SLA identifies and depicts the service requirements of the user and the level of service promised by provider. Availability of enormous service solutions is troublesome for cloud users in selecting the right service provider both in terms of price and the degree of promised services. On the other end a service provider need a centralized and reliable QoS repository and assessment framework that help them in offering an optimal amount of marginal resources to requested consumer. Although there are number of existing literatures that assist the interaction parties to achieve their desired goal in some way, however, there are still many gaps that need to be filled for establishing and maintaining a trusted relationship between them. In this paper we tried to identify all those gaps that is necessary for a trusted relationship between a service provider and service consumer. The aim of this research is to present an overview of the existing literature and compare them based on different criteria such as QoS integration, QoS repository, QoS filtering, trusted relationship and an SLA.
{"title":"The Need of an Optimal QoS Repository and Assessment Framework in Forming a Trusted Relationship in Cloud: A Systematic Review","authors":"A. Alghamdi, Walayat Hussain, Abdulaziz Alharthi, Abdulla Badar Almusheqah","doi":"10.1109/ICEBE.2017.55","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.55","url":null,"abstract":"Due to the cost-effectiveness and scalable features of the cloud the demand of its services is increasing every next day. Quality of Service (QOS) is one of the crucial factor in forming a viable Service Level Agreement (SLA) between a consumer and the provider that enable them to establish and maintain a trusted relationship with each other. SLA identifies and depicts the service requirements of the user and the level of service promised by provider. Availability of enormous service solutions is troublesome for cloud users in selecting the right service provider both in terms of price and the degree of promised services. On the other end a service provider need a centralized and reliable QoS repository and assessment framework that help them in offering an optimal amount of marginal resources to requested consumer. Although there are number of existing literatures that assist the interaction parties to achieve their desired goal in some way, however, there are still many gaps that need to be filled for establishing and maintaining a trusted relationship between them. In this paper we tried to identify all those gaps that is necessary for a trusted relationship between a service provider and service consumer. The aim of this research is to present an overview of the existing literature and compare them based on different criteria such as QoS integration, QoS repository, QoS filtering, trusted relationship and an SLA.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129398646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Guangyi Xiao, Jiqian Mo, Even Chow, Hao Chen, J. Guo, Zhiguo Gong
This paper proposes a multi-task learning algorithm to classify the Chinese legal questions using deep convolutional neural networks (CNN). First, we propose a multi-task Convolutional Neural Network (CNN) for classification of Chinese legal questions with trainable word embedding where coarse grained classification is the main task and fine grained classification is the side task. Second, we develop a hierarchical classification model which takes the output of coarse classification as one part of the input for fine grained classification. We find that the side task can improve the accuracy and efficiency of the classification in a certain extent. Our experiments on the entire Chinese Legal Questions Dataset (LQDS) demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using almost all data in LQDS for classification and we achieve the state of the art performance.
{"title":"Multi-Task CNN for Classification of Chinese Legal Questions","authors":"Guangyi Xiao, Jiqian Mo, Even Chow, Hao Chen, J. Guo, Zhiguo Gong","doi":"10.1109/ICEBE.2017.22","DOIUrl":"https://doi.org/10.1109/ICEBE.2017.22","url":null,"abstract":"This paper proposes a multi-task learning algorithm to classify the Chinese legal questions using deep convolutional neural networks (CNN). First, we propose a multi-task Convolutional Neural Network (CNN) for classification of Chinese legal questions with trainable word embedding where coarse grained classification is the main task and fine grained classification is the side task. Second, we develop a hierarchical classification model which takes the output of coarse classification as one part of the input for fine grained classification. We find that the side task can improve the accuracy and efficiency of the classification in a certain extent. Our experiments on the entire Chinese Legal Questions Dataset (LQDS) demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using almost all data in LQDS for classification and we achieve the state of the art performance.","PeriodicalId":347774,"journal":{"name":"2017 IEEE 14th International Conference on e-Business Engineering (ICEBE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131540620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：